Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds match behavior the annotations cannot convey (exact substring, case-insensitive) and, importantly, describes the chained workflow: snippets carry a chapterId and an offset to pass to read_chapter. That is genuine behavioral context beyond structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, each earning its place: what it searches, how to scope it, what it returns, and why to prefer it over reading chapters. The routing advice is placed last, after the mechanics, which is the right ordering.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description compensates by describing the return payload (snippets with chapterId and offset) and the follow-up call to read_chapter. Combined with the schema's full parameter coverage, an agent has everything needed to invoke and use the result correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds semantics the schema omits: matching is exact and case-insensitive, and storyId narrows the search to a single story rather than just 'Limit the search to one story.' Those details affect how an agent crafts the query.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Find a word or phrase in the user's own stories') and immediately qualifies the match semantics as exact and case-insensitive. It also scopes the search space (every story, or one story via storyId), which separates it from siblings like search_entries and get_story.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes the agent away from a sibling: 'Use this to find a moment instead of reading chapters one by one,' naming the read_chapter workflow it replaces. It also states the two scoping modes. It stops short of an explicit when-not-to-use (e.g., when to use search_entries instead), so it falls just shy of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.